搜索到
60
篇与
的结果
-
js replace全部替换的方法 js replace全部替换的方法replace替换第一次出现的字符串 var str = '我在中国北方纯正的中国北方人'; var newstr=str.replace('北方','南方'); console.log(newstr); //我在中国南方纯正的中国南方人使用正则替换字符串中匹配的所有字符串（实现replaceAll效果） var str = '我在中国北方纯正的中国北方人'; var reg = new RegExp( '北方' , "g" ) var newstr = str.replace( reg , '南方' ); console.log(newstr); //我在中国南方纯正的中国南方人封装成replaceAll挂载到原型链String.prototype.replaceAll=function(a,b){//吧a替换成b var reg=new RegExp(a,"g"); //创建正则RegExp对象 return this.replace(reg,b); } //实例 var str = '我在中国北方纯正的中国北方人'; var newstr=str.replaceAll('北方','南方'); console.log(newstr); //我在中国南方纯正的中国南方人参考资料js replace全部替换的方法:https://blog.csdn.net/nizhengjia888/article/details/84143650 -
python实现阿里云域名ipv4和ipv6 ddns 1.前言首先得有一个阿里云的域名：https://www.aliyun.com/minisite/goods?userCode=jdjc69nf然后你的IP必须是公网IP，不然解析了也没用。本文章讲怎样通过阿里云的SDK来添加修改域名解析，检查本机IP与解析的IP是否一致，不一致自动修改解析，达到动态解析的目的，主要用于家庭宽带这些动态IP的地方。2.安装阿里云SDK和其他第三方库pip install aliyun-python-sdk-core-v3 pip install aliyun-python-sdk-domain pip install aliyun-python-sdk-alidns pip install requests3.获取accessKeyId和accessSecret可以在阿里云控制台个人中心直接获取，但是一般建议使用RAM角色来进行权限控制，这样这个accessKey和accessSecret就只能操作域名，不能操作其他的资源，相对会比较安全。关于RAM快速入门：https://help.aliyun.com/document_detail/28637.html?source=5176.11533457&userCode=jdjc69nf4.源码下载-官方4.1 下载地址gitee：https://gitee.com/zeruns/aliddns_Pythongithub：https://github.com/zeruns/-Python-aliddns_ipv4-ipv6将aliddns.py文件下载下来。然后用notepad++或其他编辑器打开，按照注释提示修改并保存。然后运行一下看看有没有问题：打开cmd输入python 脚本目录4.2源码备份from aliyunsdkcore.client import AcsClient from aliyunsdkcore.acs_exception.exceptions import ClientException from aliyunsdkcore.acs_exception.exceptions import ServerException from aliyunsdkalidns.request.v20150109.DescribeSubDomainRecordsRequest import DescribeSubDomainRecordsRequest from aliyunsdkalidns.request.v20150109.DescribeDomainRecordsRequest import DescribeDomainRecordsRequest import requests from urllib.request import urlopen import json ipv4_flag = 1 # 是否开启ipv4 ddns解析,1为开启，0为关闭 ipv6_flag = 1 # 是否开启ipv6 ddns解析,1为开启，0为关闭 accessKeyId = "accessKeyId" # 将accessKeyId改成自己的accessKeyId accessSecret = "accessSecret" # 将accessSecret改成自己的accessSecret domain = "4v7p.top" # 你的主域名 name_ipv4 = "ipv4.test" # 要进行ipv4 ddns解析的子域名 name_ipv6 = "ipv6.test" # 要进行ipv6 ddns解析的子域名 client = AcsClient(accessKeyId, accessSecret, 'cn-hangzhou') def update(RecordId, RR, Type, Value): # 修改域名解析记录 from aliyunsdkalidns.request.v20150109.UpdateDomainRecordRequest import UpdateDomainRecordRequest request = UpdateDomainRecordRequest() request.set_accept_format('json') request.set_RecordId(RecordId) request.set_RR(RR) request.set_Type(Type) request.set_Value(Value) response = client.do_action_with_exception(request) def add(DomainName, RR, Type, Value): # 添加新的域名解析记录 from aliyunsdkalidns.request.v20150109.AddDomainRecordRequest import AddDomainRecordRequest request = AddDomainRecordRequest() request.set_accept_format('json') request.set_DomainName(DomainName) request.set_RR(RR) # https://blog.zeruns.tech request.set_Type(Type) request.set_Value(Value) response = client.do_action_with_exception(request) if ipv4_flag == 1: request = DescribeSubDomainRecordsRequest() request.set_accept_format('json') request.set_DomainName(domain) request.set_SubDomain(name_ipv4 + '.' + domain) response = client.do_action_with_exception(request) # 获取域名解析记录列表 domain_list = json.loads(response) # 将返回的JSON数据转化为Python能识别的 ip = urlopen('https://api-ipv4.ip.sb/ip').read() # 使用IP.SB的接口获取ipv4地址 ipv4 = str(ip, encoding='utf-8') print("获取到IPv4地址：%s" % ipv4) if domain_list['TotalCount'] == 0: add(domain, name_ipv4, "A", ipv4) print("新建域名解析成功") elif domain_list['TotalCount'] == 1: if domain_list['DomainRecords']['Record'][0]['Value'].strip() != ipv4.strip(): update(domain_list['DomainRecords']['Record'][0]['RecordId'], name_ipv4, "A", ipv4) print("修改域名解析成功") else: # https://blog.zeruns.tech print("IPv4地址没变") elif domain_list['TotalCount'] > 1: from aliyunsdkalidns.request.v20150109.DeleteSubDomainRecordsRequest import DeleteSubDomainRecordsRequest request = DeleteSubDomainRecordsRequest() request.set_accept_format('json') request.set_DomainName(domain) # https://blog.zeruns.tech request.set_RR(name_ipv4) response = client.do_action_with_exception(request) add(domain, name_ipv4, "A", ipv4) print("修改域名解析成功") print("本程序版权属于zeruns，博客：https://blog.zeruns.tech") if ipv6_flag == 1: request = DescribeSubDomainRecordsRequest() request.set_accept_format('json') request.set_DomainName(domain) request.set_SubDomain(name_ipv6 + '.' + domain) response = client.do_action_with_exception(request) # 获取域名解析记录列表 domain_list = json.loads(response) # 将返回的JSON数据转化为Python能识别的 ip = urlopen('https://api-ipv6.ip.sb/ip').read() # 使用IP.SB的接口获取ipv6地址 ipv6 = str(ip, encoding='utf-8') print("获取到IPv6地址：%s" % ipv6) if domain_list['TotalCount'] == 0: add(domain, name_ipv6, "AAAA", ipv6) print("新建域名解析成功") elif domain_list['TotalCount'] == 1: if domain_list['DomainRecords']['Record'][0]['Value'].strip() != ipv6.strip(): update(domain_list['DomainRecords']['Record'][0]['RecordId'], name_ipv6, "AAAA", ipv6) print("修改域名解析成功") else: # https://blog.zeruns.tech print("IPv6地址没变") elif domain_list['TotalCount'] > 1: from aliyunsdkalidns.request.v20150109.DeleteSubDomainRecordsRequest import DeleteSubDomainRecordsRequest request = DeleteSubDomainRecordsRequest() request.set_accept_format('json') request.set_DomainName(domain) request.set_RR(name_ipv6) # https://blog.zeruns.tech response = client.do_action_with_exception(request) add(domain, name_ipv6, "AAAA", ipv6) print("修改域名解析成功")6.设置定时任务6.1 Linux操作使用crontab -e写入定时任务即可。例如：6.2 windows操作右键点击电脑左下角，再点击计算机管理点击任务计划程序，再点击创建任务，输入要设置的任务名称。新建触发器，执行间隔可以自己设置，持续时间改成无限期。新建操作，这一步很重要，配置错误就会导致脚本文件执行不成功！！！最后确认就行。参考资料Python实现阿里云域名DDNS支持ipv4和ipv6：https://developer.aliyun.com/article/755182
-
Python图片处理库PIL的使用 Python图片处理库PIL的使用1.加载图片、查看文件信息1.1加载图片。图片地址可以是相对路径，也可以是相对路径如果文件打开失败, 将抛出IOError异常。from PIL import Image img = Image.open(图片地址)1.2显示图片img.show()1.3查看图片属性format属性指定了图像文件的格式，如果图像不是从文件中加载的则为None。size属性是一个2个元素的元组，包含图像宽度和高度（像素）。mode属性定义了像素格式，常用的像素格式为：“L” (luminance) - 灰度图, “RGB” , “CMYK”。print(img.format, img.size, img.mode)JPEG (750, 300) RGB1.4 保存图片img.save("./save.jpg")2.使用滤镜2.0 使用方式from PIL import ImageFilter #滤镜所需要的包 img.filter(滤镜效果)常用滤镜有如下：滤镜名称含义ImageFilter.BLUR模糊滤镜ImageFilter.CONTOUR轮廓ImageFilter.EDGE_ENHANCE边界加强ImageFilter.EDGE_ENHANCE_MORE边界加强(阀值更大)ImageFilter.EMBOSS浮雕滤镜ImageFilter.FIND_EDGES边界滤镜ImageFilter.SMOOTH平滑滤镜ImageFilter.SMOOTH_MORE平滑滤镜(阀值更大)ImageFilter.SHARPEN锐化滤镜2.1滤镜效果图原图模糊-ImageFilter.BLUR轮廓(铅笔画)-ImageFilter.CONTOUR边界加强-ImageFilter.EDGE_ENHANCE边界加强(阀值更大)-ImageFilter.EDGE_ENHANCE_MORE浮雕-ImageFilter.EMBOSS边界-ImageFilter.FIND_EDGES（其实相当于背景涂黑，线条白色）平滑-ImageFilter.SMOOTH平滑(阀值更大)-ImageFilter.SMOOTH_MORE锐化-ImageFilter.SHARPEN2.2 自定义滤镜class SELF_FILTER(ImageFilter.BuiltinFilter): name = "SELF_FILTER" filterargs=(3,3),2,0,( -1,-1,-1, -1,9,-1, -1,-1,-1, ) result = img.filter(SELF_FILTER) result.show()3.图像局部切割# 导包 from PIL import Image # 加载图片 img = Image.open("./img.jpg") # 查看图片大小 print(img.size) #(750, 300) # 设置切割范围 （点1x,点1y,点2x,点2y） area = (170,80,580,240) # 切割图片 img_crop = img.crop(area) # 查看结果 img_crop.show()4.图像粘贴(叠加)# 导包 from PIL import Image # 准备图片 img = Image.open("./img.jpg") area = Image.open("./area.jpg") # 图片(粘贴)叠加 会直接改变原图，不产生新的图片 # 格式：图片1.paste(图片2，位置) 位置为左上角的(x,y) img.paste(area,(0,0)) # 查看效果 img.show()5.图像拼接--通过图像粘贴(叠加)实现# 导包 from PIL import Image # 准备图片 img1 = Image.open("./img.jpg") img2 = Image.open("./img.jpg") # 创建拼接结果的空白图：new(模式，大小，颜色) """ 模式：'RGB'/'RGBA' 大小：(width,height) 颜色：(R,G,B) """ empty = Image.new('RGB',(750,600),(255,255,255)) # 通过图像粘贴(叠加)实现图片拼接 empty.paste(img1,(0,0)) empty.paste(img2,(0,300)) # 查看效果 empty.show()结果6.图片缩放--会按比例缩放，不会拉伸# 导包 from PIL import Image # 准备图片 img = Image.open("./img.jpg") print(img.size) #(750, 300) # 缩放 -- 直接修改原图，不产生新图 new_size = (375,150) img.thumbnail(new_size) print(img.size) #(375, 150) # 查看效果 img.show()结果(750, 300) (375, 150)7.镜像翻转7.1 左右镜像# 导包 from PIL import Image # 准备图片 img = Image.open("./img.jpg") # 左右镜像 img_lr = img.transpose(Image.FLIP_LEFT_RIGHT) # 查看效果 img_lr原图：7.2 上下镜像# 导包 from PIL import Image # 准备图片 img = Image.open("./img.jpg") # 上下镜像 img_tb = img.transpose(Image.FLIP_TOP_BOTTOM) # 查看效果 img_tb镜像图8. 文字水印-把文字写到图上# 导包 from PIL import Image,ImageFont,ImageDraw # 准备图片 img = Image.open("./img.jpg") # 创建字体对象 # ImageFont.truetype(字体文件,字号) 笔 font = ImageFont.truetype('./BOD_B.TTF',60) # 创建draw对象 纸 draw = ImageDraw.Draw(img) # 文字渲染 # draw.text(坐标，文字内容，font = 字体对象，fill = 文字颜色) draw.text((0,0),"Hello World",font = font,fill = (255,0,0)) # 查看效果 img.show()结果9. 生成简单的数字验证码# 导包 from PIL import Image,ImageFont,ImageDraw import random # 创建空白图片 img = Image.new('RGB',(120,60),(255,255,255)) # 渲染背景 draw = ImageDraw.Draw(img) for i in range(0,120): for j in range(0,60): r = random.randint(60,255) g = random.randint(60,255) b = random.randint(60,255) draw.point((i,j),(r,g,b)) # 背景模糊 img = img.filter(ImageFilter.BLUR) # 渲染文字 draw = ImageDraw.Draw(img) font = ImageFont.truetype('./BOD_B.TTF',40) draw.text((20,10),"2345",font = font,fill = (0,0,0)) # 查看效果 img.show()参考资料python pil 第三方库实战之三：ImageFilter滤镜小试：https://blog.csdn.net/kanwenzhang/article/details/51936742PIL告诉你这么处理图片让你不再加班处理图片：https://www.bilibili.com/video/BV1yE411L7dR?p=11&spm_id_from=pageDriver
-
python下载m3u8视频 python下载m3u8视频单线程版import requests import os import re import threading # m3u8 url & vedio name m3u8_url = "https://www.hyxrzs.com/20201217/Jt4nKiPm/index.m3u8" base_url = "https://www.hyxrzs.com" vedio_name = "超人总动员" #创建用于合并的临时文件夹，用于存放ts文件 if not os.path.exists('merge'): os.system('mkdir merge') # 模拟浏览器header,防止误伤 headers = {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.100 Safari/537.36'} # 获取m3u8文件的内容 m3u8_content = requests.get(m3u8_url,headers=headers).text # 判断是否是最终的 is_final_m3u8 = not "m3u8" in m3u8_content # 当 m3u8 作为主播放列表（Master Playlist）时，其内部提供的是同一份媒体资源的多份流列表资源（Variant Stream） # 如果不是最终的m3u8,进入下一层找到最终的m3u8 （针对m3u8多分辨率适配的情况，会先有一个针对不同分辨率的m3u8索引文件） if not is_final_m3u8: # 解析出真正的m3u8_content for m3u8_url in m3u8_content.split('\n'): if "m3u8" in m3u8_url: m3u8_url = base_url +m3u8_url m3u8_content = requests.get(m3u8_url,headers=headers).text break m3u8_content_split_list = m3u8_content.split('\n') # 判断视频是否经过AES-128加密，如果加密过则获取加密方式和加密秘钥 key = '' for index,line in enumerate(m3u8_content_split_list): # 判断视频是否经过AES-128加密 if "#EXT-X-KEY" in line: #获取加密方式 method_pos = line.find("METHOD") comma_pos = line.find(",") method = line[method_pos:comma_pos].split('=')[1] print("该视频经过加密，加密方式为：", method) #获取加密密钥 uri_pos = line.find("URI") quotation_mark_pos = line.rfind('"') key_path = line[uri_pos:quotation_mark_pos].split('"')[1] key_url = m3u8_url.replace("index.m3u8",key_path) res = requests.get(key_url) key = res.content #从m3u8文件中解析出ts地址集 play_list = [] key = '' for index,line in enumerate(m3u8_content_split_list): #以下拼接方式可能会根据自己的需求进行改动 if '#EXTINF' in line: # 如果加密，直接提取每一级的.ts文件链接地址 if 'http' in m3u8_content_split_list[index + 1]: href = m3u8_content_split_list[index + 1] play_list.append(href) # 如果没有加密，直接构造出url链接 elif('ad0.ts' not in m3u8_content_split_list[index + 1]): href = base_url + m3u8_content_split_list[index+1] play_list.append(href) print("m3u8文件解析成功，共解析到",len(play_list),"个ts文件") # 封装下载当个ts文件的函数 def down_ts(index,ts_url,cryptor = False): # 获取ts content if not cryptor: ts_content = requests.get(ts_url,headers=headers).content else: ts_content = cryptor.decrypt(requests.get(ts_url,headers=headers).content)#获取bing解密ts # 写入文件 with open('merge/' + str(index+1) + '.ts','wb') as file: file.write(ts_content) print('第{}/{}个ts文件下载完成'.format(index+1,len(play_list))) # 根据ts地址集下载ts文件 print("开始下载所有的ts文件") if(len(key)):# 如果加密过 from Crypto.Cipher import AES cryptor = AES.new(key, AES.MODE_CBC, key) for index,ts_url in enumerate(play_list): down_ts(index,ts_url,cryptor) else: # 如果未加密 for index,ts_url in enumerate(play_list): down_ts(index,ts_url) print('所有ts文件都已下载完成') # 合并ts文件为mp4 并删除下载的ts文件 merge_cmd = "cat " for i in range(len(os.listdir("./merge"))): merge_cmd += "merge/"+ str(i+1) +".ts " merge_cmd += ">>vedio/"+vedio_name+".mp4" del_cmd = 'rm merge/*.ts' os.system(merge_cmd)#执行合并命令 os.system(del_cmd)#执行删除命令 print(vedio_name,'.mp4下载已完成')多线程版备注：目前该版本还存在问题(频繁下载被服务器断开连接),如过未下载完成则多次重复执行即可import requests import os import re import threading # m3u8 url & vedio name m3u8_url = "https://www.hyxrzs.com/20201217/Jt4nKiPm/index.m3u8" base_url = "https://www.hyxrzs.com" vedio_name = "超人总动员" #使用多线程技术 thread_list = [] max_connections = 2 # 定义最大线程数 pool_sema = threading.BoundedSemaphore(max_connections) # 或使用Semaphore方法 #创建用于合并的临时文件夹，用于存放ts文件 if not os.path.exists('merge'): os.system('mkdir merge') # 模拟浏览器header,防止误伤 headers = {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.100 Safari/537.36'} # 获取m3u8文件的内容 m3u8_content = requests.get(m3u8_url,headers=headers).text # 判断是否是最终的 is_final_m3u8 = not "m3u8" in m3u8_content # 当 m3u8 作为主播放列表（Master Playlist）时，其内部提供的是同一份媒体资源的多份流列表资源（Variant Stream） # 如果不是最终的m3u8,进入下一层找到最终的m3u8 （针对m3u8多分辨率适配的情况，会先有一个针对不同分辨率的m3u8索引文件） if not is_final_m3u8: # 解析出真正的m3u8_content for m3u8_url in m3u8_content.split('\n'): if "m3u8" in m3u8_url: m3u8_url = base_url +m3u8_url m3u8_content = requests.get(m3u8_url,headers=headers).text break m3u8_content_split_list = m3u8_content.split('\n') # 判断视频是否经过AES-128加密，如果加密过则获取加密方式和加密秘钥 key = '' for index,line in enumerate(m3u8_content_split_list): # 判断视频是否经过AES-128加密 if "#EXT-X-KEY" in line: #获取加密方式 method_pos = line.find("METHOD") comma_pos = line.find(",") method = line[method_pos:comma_pos].split('=')[1] print("该视频经过加密，加密方式为：", method) #获取加密密钥 uri_pos = line.find("URI") quotation_mark_pos = line.rfind('"') key_path = line[uri_pos:quotation_mark_pos].split('"')[1] key_url = m3u8_url.replace("index.m3u8",key_path) res = requests.get(key_url) key = res.content #从m3u8文件中解析出ts地址集 play_list = [] key = '' for index,line in enumerate(m3u8_content_split_list): #以下拼接方式可能会根据自己的需求进行改动 if '#EXTINF' in line: # 如果加密，直接提取每一级的.ts文件链接地址 if 'http' in m3u8_content_split_list[index + 1]: href = m3u8_content_split_list[index + 1] play_list.append(href) # 如果没有加密，直接构造出url链接 elif('ad0.ts' not in m3u8_content_split_list[index + 1]): href = base_url + m3u8_content_split_list[index+1] play_list.append(href) print("m3u8文件解析成功，共解析到",len(play_list),"个ts文件") print("上次下载完成了",len(os.listdir("./merge")),"个ts文件") # 封装下载当个ts文件的函数 def down_ts(index,ts_url,cryptor = False): # 获取ts content if not cryptor: ts_content = requests.get(ts_url,headers=headers).content else: ts_content = cryptor.decrypt(requests.get(ts_url,headers=headers).content)#获取bing解密ts # 写入文件 with open('merge/' + str(index+1) + '.ts','wb') as file: file.write(ts_content) print('第{}/{}个ts文件下载完成'.format(index+1,len(play_list))) # 根据ts地址集下载ts文件 print("开始下载所有的ts文件") if(len(key)):# 如果加密过 from Crypto.Cipher import AES cryptor = AES.new(key, AES.MODE_CBC, key) for index,ts_url in enumerate(play_list): if os.path.exists('merge/' + str(index+1) + '.ts'):continue #跳过已经存在的ts文件 thread_list.append(threading.Thread(target=down_ts, args=(index,ts_url,cryptor))) else: # 如果未加密 for index,ts_url in enumerate(play_list): if os.path.exists('merge/' + str(index+1) + '.ts'):continue #跳过已经存在的ts文件 thread_list.append(threading.Thread(target=down_ts, args=(index,ts_url))) for t in thread_list: t.start() for t in thread_list: t.join() # 子线程全部加入，主线程等所有子线程运行完毕 if len(os.listdir("./merge"))==len(play_list): print('所有ts文件都已下载完成') # 合并ts文件为mp4 并删除下载的ts文件 merge_cmd = "cat " for i in range(len(os.listdir("./merge"))): merge_cmd += "merge/"+ str(i+1) +".ts " merge_cmd += ">>vedio/"+vedio_name+".mp4" del_cmd = 'rm merge/*.ts' os.system(merge_cmd)#执行合并命令 os.system(del_cmd)#执行删除命令 print(vedio_name,'.mp4下载已完成') else: print("下载发生错误,请重新运行，下载完成度{}/{}".format(len(os.listdir("./merge")),len(play_list)))参考资料m3u8 文件格式详解:https://www.jianshu.com/p/e97f6555a070
-
python实现汉字转拼音 python实现汉字转拼音所用模块xpinyin模块安装pip install xpinyin使用方式from xpinyin import Pinyin p = Pinyin() pinyin = p.get_pinyin("上海") # shang-hai print(pinyin) # 显示声调1 pinyin = p.get_pinyin("上海", tone_marks=True) #shang4-hai3 print(pinyin) # 显示声调 pinyin = p.get_pinyin("上海", tone_marks='marks') #shàng-hǎi print(pinyin) # 设置分隔符 pinyin = p.get_pinyin("上海", ' ') # 'shang hai' print(pinyin) # 只显示声母 pinyin = p.get_initial("上") # 'S' print(pinyin) # 显示多字声母，并设置分隔符 p.get_initials("上海", '') #'SH' print(pinyin)shang-hai shang4-hai3 shàng-hǎi shang hai S S
-
ajax标准请求 ajax标准请求ajax$.ajax({ url:"http://url...", dataType:"json", async:true, data:{"id":"value"}, type:"GET", beforeSend:function(){ }, success:function(data){ }, complete:function(){ }, error:function(){ } });GET$.get("/", {"key": "val"}, res=>{ alert(res); });POST$.post("/", {"key": "val"}, res=>{ alert(res); }, "json");
-
[www.cc148.com]小说爬虫 [www.cc148.com]小说爬虫from bs4 import BeautifulSoup from urllib.request import urlopen from progressbar import * #根据目录页面地址获取目录页面的html、并封装为soup catalogue_url = "https://www.cc148.com/19_19568/" html = urlopen(catalogue_url).read().decode('gbk') soup = BeautifulSoup(html, features='lxml') #根据目录页html获取到小说的titile title = soup.title.text.split("最新章节列表")[0] #根据目录页html获取到小说每一章的地址集合chapter_url_list chapter_url_list = [] for dd in soup.find_all('dd'): chapter_url = catalogue_url + dd.a["href"] chapter_url_list.append(chapter_url) # 加入进度条功能 widgets = ['正在下载--'+title,Percentage(), ' ', Bar('#'),' ', Timer(),' ', ETA()] pbar = ProgressBar(widgets=widgets, maxval=len(chapter_url_list)).start() count = 0 #根据chapter_url_list逐章下载并保存到当前文件夹 txt_file_name = title + ".txt" with open(txt_file_name,'w') as f: for chapter_url in chapter_url_list: chapter_html = urlopen(chapter_url).read().decode('gbk') chapter_soup = BeautifulSoup(chapter_html, features='lxml') chapter_title = chapter_soup.title.text.split('_')[0] chapter_content = chapter_soup.find("div",{"id":"content"}).text chapter_text = chapter_title + "\n" + chapter_content + "\n" f.write(chapter_text) count +=1 pbar.update(count) pbar.finish()
-
Python中xml、字典、EasyDict、json格式相互转换(包含json格式化和xml格式化) Python中xml、字典、EasyDict、json格式相互转换(包含json格式化和xml格式化)依赖包jsonxmltodictxml转字典import xmltodict xmlstr =""" <student> <stid>10213</stid> <info> <name>name</name> <sex>male</sex> </info> <course> <name>math</name> <score>90</score> </course> </student> """ #parse是的xml解析器 dict_ = xmltodict.parse(xmlstr) print(dict_)OrderedDict([('student', OrderedDict([('stid', '10213'), ('info', OrderedDict([('name', 'name'), ('sex', 'male')])), ('course', OrderedDict([('name', 'math'), ('score', '90')]))]))])字典转EasyDictimport xmltodict xmlstr =""" <student> <stid>10213</stid> <info> <name>name</name> <sex>male</sex> </info> <course> <name>math</name> <score>90</score> </course> </student> """ #parse是的xml解析器 dict_ = xmltodict.parse(xmlstr) #转EasyDict from easydict import EasyDict dict_ = EasyDict(dict_) print(dict_){'student': {'stid': '10213', 'info': {'name': 'name', 'sex': 'male'}, 'course': {'name': 'math', 'score': '90'}}}字典转json最简版import json dict_ = { 'name': 'Jack', 'age': 22, 'skills': ['Python', 'Java', 'C++', 'Matlab'], 'major': '计算机技术', 'english': '英语六级', 'school': 'WIT' } #json库dumps()是将dict转化成json格式，loads()是将json转化成dict格式。 #dumps()方法的ident=1，格式化json jsonstr = json.dumps(dict_) print(jsonstr){"name": "Jack", "age": 22, "skills": ["Python", "Java", "C++", "Matlab"], "major": "\u8ba1\u7b97\u673a\u6280\u672f", "english": "\u82f1\u8bed\u516d\u7ea7", "school": "WIT"}很明显中文字符被转化了，于是使用：ensure_ascii=Falseimport json dict_ = { 'name': 'Jack', 'age': 22, 'skills': ['Python', 'Java', 'C++', 'Matlab'], 'major': '计算机技术', 'english': '英语六级', 'school': 'WIT' } #json库dumps()是将dict转化成json格式，loads()是将json转化成dict格式。 #dumps()方法的ident=1，格式化json jsonstr = json.dumps(dict_,ensure_ascii=False) print(jsonstr){"name": "Jack", "age": 22, "skills": ["Python", "Java", "C++", "Matlab"], "major": "计算机技术", "english": "英语六级", "school": "WIT"}加入行缩进import json dict_ = { 'name': 'Jack', 'age': 22, 'skills': ['Python', 'Java', 'C++', 'Matlab'], 'major': '计算机技术', 'english': '英语六级', 'school': 'WIT' } #json库dumps()是将dict转化成json格式，loads()是将json转化成dict格式。 #dumps()方法的ident=1，格式化json jsonstr = json.dumps(dict_,indent=2) #indent=2 表示行缩进=2 print(jsonstr){ "name": "Jack", "age": 22, "skills": [ "Python", "Java", "C++", "Matlab" ], "major": "\u8ba1\u7b97\u673a\u6280\u672f", "english": "\u82f1\u8bed\u516d\u7ea7", "school": "WIT" }很明显中文字符被转化了，于是使用：ensure_ascii=Falseimport json dict_ = { 'name': 'Jack', 'age': 22, 'skills': ['Python', 'Java', 'C++', 'Matlab'], 'major': '计算机技术', 'english': '英语六级', 'school': 'WIT' } #json库dumps()是将dict转化成json格式，loads()是将json转化成dict格式。 #dumps()方法的ident=1，格式化json jsonstr = json.dumps(dict_,indent=2,ensure_ascii=False) #indent=2 表示行缩进=2 print(jsonstr){ "name": "Jack", "age": 22, "skills": [ "Python", "Java", "C++", "Matlab" ], "major": "计算机技术", "english": "英语六级", "school": "WIT" }json转字典json.loads(json串)，将json字符串转化成字典import json jsonstr = """ { "name": "Jack", "age": 22, "skills": [ "Python", "Java", "C++", "Matlab" ], "major": "计算机技术", "english": "英语六级", "school": "WIT" } """ dict_ = json.loads(jsonstr) print(dict_){'name': 'Jack', 'age': 22, 'skills': ['Python', 'Java', 'C++', 'Matlab'], 'major': '计算机技术', 'english': '英语六级', 'school': 'WIT'}字典转xmlimport xmltodict dict_ = {'student': {'course': {'name': 'math', 'score': '90'}, 'info': {'sex': 'male', 'name': 'name'}, 'stid': '10213'}} xmlstr = xmltodict.unparse(dict_) print(xmlstr)<?xml version="1.0" encoding="utf-8"?> <student><course><name>math</name><score>90</score></course><info><sex>male</sex><name>name</name></info><stid>10213</stid></student>XML格式化(美化)import xmltodict dict_ = {'student': {'course': {'name': 'math', 'score': '90'}, 'info': {'sex': 'male', 'name': 'name'}, 'stid': '10213'}} xmlstr = xmltodict.unparse(dict_) from xml.dom import minidom xml = minidom.parseString(xmlstr) xml_pretty_str = xml.toprettyxml() print(xml_pretty_str)<?xml version="1.0" encoding="utf-8"?> <student> <course> <name>math</name> <score>90</score> </course> <info> <sex>male</sex> <name>name</name> </info> <stid>10213</stid> </student>参考资料Python中xml和json格式相互转换操作示例：https://www.jb51.net/article/152118.htmPython json读写方式和字典相互转化:https://www.jb51.net/article/184983.htmPython如何优雅的格式化XML 【Python XML Format】: https://blog.csdn.net/qq_41958123/article/details/105357692
-
progressbar:python进度条功能 1.安装progressbar安装：pip install progressbar2.使用2.1 用法一import time from progressbar import * total = 1000 def dosomework(): time.sleep(0.01) progress = ProgressBar() for i in progress(range(1000)): dosomework()用法一显示效果5% |### | 100% |#########################################################################|2.2 用法二import time from progressbar import * total = 1000 def dosomework(): time.sleep(0.01) pbar = ProgressBar().start() for i in range(1000): pbar.update(int((i / (total - 1)) * 100)) dosomework() pbar.finish()用法二显示效果5% |### | 100% |#########################################################################|2.3 用法三import time from progressbar import * total = 1000 def dosomework(): time.sleep(0.01) widgets = ['Progress: ',Percentage(), ' ', Bar('#'),' ', Timer(),' ', ETA(), ' ', FileTransferSpeed()] pbar = ProgressBar(widgets=widgets, maxval=10*total).start() for i in range(total): # do something pbar.update(10 * i + 1) dosomework() pbar.finish()widgets可选参数含义：Progress: ' ：设置进度条前显示的文字Percentage() ：显示百分比Bar('#') ： 设置进度条形状Timer() ：显示已用时间ETA() ： 显示预计剩余时间用法三显示效果Progress: 100% |#############| Elapsed Time: 0:00:10 Time: 0:00:10 981.79 B/s
-
Python中将dataframe转换为字典 Python中将dataframe转换为字典有时候，在Python中需要将dataframe类型转换为字典类型，下面的方法帮助我们解决这一问题。构造dataframeimport pandas as pd a = ['Name', 'Age', 'Gender'] b = ['Ali', '19', 'China'] data = pd.DataFrame(zip(a, b), columns=['project', 'attribute']) print datadataframe转换为字典dict_country = data.set_index('project').T.to_dict('list') print dict_country结果 project attribute 0 Name Ali 1 Age 19 2 Gender China {'Gender': ['China'], 'Age': ['19'], 'Name': ['Ali']}注意事项转置之前需要设置指定的索引，否则会按照默认索引转换成这样：{0: ['Name', 'Ali'], 1: ['Age', '19'], 2: ['Gender', 'China']}参考资料Python中将dataframe转换为字典：https://blog.csdn.net/yuanxiang01/article/details/79634632
-
Python中的三目运算符 Python中的三目运算符语法格式Python语言不像Java、JavaScript等这些语言有类似： 判段的条件?条件为真时的结果:条件为假时的结果这样的三目运算，但是Python也有自己的三目运算符： 条件为真时的结果 if 判段的条件 else 条件为假时的结果举例例一：编写一个Python程序，输入两个数，比较它们的大小并输出其中较大者。x = int(input("please enter first integer:")) y = int(input("please enter second integer:")) #一般的写法 if (x == y): print("两数相同！") elif(x > y): print("较大的数为：",x) else: print("较大的数为：",y) # 三目运算符写法 print(x if(x>y) else y)
-
Python将字典中的键值对反转方法 Python将字典中的键值对反转方法应用背景（问题示例）src:{'1': 0, '10': 1, '100': 2, '11': 3, '12': 4, '13': 5, '14': 6, '15': 7, '16': 8, '17': 9, '18': 10, '19': 11, '2': 12, '20': 13, '21': 14, '22': 15, '23': 16, '24': 17, '25': 18, '26': 19, '27': 20, '28': 21, '29': 22, '3': 23, '30': 24, '31': 25, '32': 26, '33': 27, '34': 28, '35': 29, '36': 30, '37': 31, '38': 32, '39': 33, '4': 34, '40': 35, '41': 36, '42': 37, '43': 38, '44': 39, '45': 40, '46': 41, '47': 42, '48': 43, '49': 44, '5': 45, '50': 46, '51': 47, '52': 48, '53': 49, '54': 50, '55': 51, '56': 52, '57': 53, '58': 54, '59': 55, '6': 56, '60': 57, '61': 58, '62': 59, '63': 60, '64': 61, '65': 62, '66': 63, '67': 64, '68': 65, '69': 66, '7': 67, '70': 68, '71': 69, '72': 70, '73': 71, '74': 72, '75': 73, '76': 74, '77': 75, '78': 76, '79': 77, '8': 78, '80': 79, '81': 80, '82': 81, '83': 82, '84': 83, '85': 84, '86': 85, '87': 86, '88': 87, '89': 88, '9': 89, '90': 90, '91': 91, '92': 92, '93': 93, '94': 94, '95': 95, '96': 96, '97': 97, '98': 98, '99': 99}dst:{0: '1', 1: '10', 2: '100', 3: '11', 4: '12', 5: '13', 6: '14', 7: '15', 8: '16', 9: '17', 10: '18', 11: '19', 12: '2', 13: '20', 14: '21', 15: '22', 16: '23', 17: '24', 18: '25', 19: '26', 20: '27', 21: '28', 22: '29', 23: '3', 24: '30', 25: '31', 26: '32', 27: '33', 28: '34', 29: '35', 30: '36', 31: '37', 32: '38', 33: '39', 34: '4', 35: '40', 36: '41', 37: '42', 38: '43', 39: '44', 40: '45', 41: '46', 42: '47', 43: '48', 44: '49', 45: '5', 46: '50', 47: '51', 48: '52', 49: '53', 50: '54', 51: '55', 52: '56', 53: '57', 54: '58', 55: '59', 56: '6', 57: '60', 58: '61', 59: '62', 60: '63', 61: '64', 62: '65', 63: '66', 64: '67', 65: '68', 66: '69', 67: '7', 68: '70', 69: '71', 70: '72', 71: '73', 72: '74', 73: '75', 74: '76', 75: '77', 76: '78', 77: '79', 78: '8', 79: '80', 80: '81', 81: '82', 82: '83', 83: '84', 84: '85', 85: '86', 86: '87', 87: '88', 88: '89', 89: '9', 90: '90', 91: '91', 92: '92', 93: '93', 94: '94', 95: '95', 96: '96', 97: '97', 98: '98', 99: '99'}具体方法第一种：dict={"a":1,"b":2,"c":3} inverse_dic={} for key,val in dict.items(): inverse_dic[val]=key第二种（推荐）：dict_list={"a":1,"b":2,"c":3} inverse_dict=dict([val,key] for key,val in dict_list.items())第三种：dict_list={"a":1,"b":2,"c":3} mydict_new=dict(zip(dict_list.values(),dict_list.keys())参考资料Python将字典中的键值对反转方法：https://blog.csdn.net/ityti/article/details/85098699
-
Python3实现局域网存活主机扫描(多线程) Python3实现局域网存活主机扫描import os import time import platform import threading def get_os(): ''''' get os 类型 ''' os = platform.system() if os == "Windows": return "n" else: return "c" def ping_ip(ip_str): cmd = ["ping", "-{op}".format(op=get_os()), "1", ip_str] output = os.popen(" ".join(cmd)).readlines() flag = False for line in list(output): if not line: continue if str(line).upper().find("TTL") >=0: flag = True break if flag: print("ip: %s is ok ***"%ip_str) def find_ip(ip_prefix): ''''' 给出当前的127.0.0 ，然后扫描整个段所有地址 ''' for i in range(1,256): ip = '%s.%s'%(ip_prefix,i) t = threading.Thread(target=ping_ip, args=(ip,)) # 注意传入的参数一定是一个元组! t.start() if __name__ == "__main__": print("start time %s"%time.ctime()) ip_prefix = "10.1.130" find_ip(ip_prefix) print("end time %s"%time.ctime())
-
被窝网电视剧爬虫 被窝网电视剧爬虫#抓取电视剧 from bs4 import BeautifulSoup from urllib.request import urlopen import urllib import re import requests import os from tqdm import tqdm def download_from_url(url, dst): """ @param: url to download file @param: dst place to put the file :return: bool """ # 获取文件长度 try: file_size = int(urlopen(url).info().get('Content-Length', -1)) except Exception as e: print(e) print("错误，访问url: %s 异常" % url) return False # 判断本地文件存在时 if os.path.exists(dst): # 获取文件大小 first_byte = os.path.getsize(dst) else: # 初始大小为0 first_byte = 0 # 判断大小一致，表示本地文件存在 if first_byte >= file_size: print("文件已经存在,无需下载") return file_size header = {"Range": "bytes=%s-%s" % (first_byte, file_size)} pbar = tqdm( total=file_size, initial=first_byte, unit='B', unit_scale=True, desc=url.split('/')[-1]) # 访问url进行下载 req = requests.get(url, headers=header, stream=True) try: with(open(dst, 'ab')) as f: for chunk in req.iter_content(chunk_size=1024): if chunk: f.write(chunk) pbar.update(1024) except Exception as e: print(e) return False pbar.close() return True #网站根地址 web_base_url="http://10.1.48.113/" vedio_episodes_page_url_list=[ "http://10.1.48.113/shipin/dianshijuji/2018-09-29/193.php", "http://10.1.48.113/shipin/dianshijuji/2018-10-26/242.php", "http://10.1.48.113/shipin/dianshijuji/2018-10-26/239.php", "http://10.1.48.113/shipin/dianshijuji/2018-10-26/240.php", "http://10.1.48.113/shipin/dianshijuji/2018-10-26/238.php", "http://10.1.48.113/shipin/dianshijuji/2018-09-22/157.php" ] for vedio_episodes_page_url in vedio_episodes_page_url_list: #逐部电视剧解析 try: vedio_episodes_page_html = urlopen(vedio_episodes_page_url).read().decode('utf-8') vedio_episodes_page_soup = BeautifulSoup(vedio_episodes_page_html, features='lxml') #解析出电视剧名和设置保存文件夹 vedio_name=vedio_episodes_page_soup.head.find_all("meta")[2]["content"].replace(" ","") vedio_save_dir="./"+vedio_name if not os.path.exists(vedio_save_dir): os.mkdir(vedio_save_dir) #解析出单集播放页面地址 vedio_episode_href_list=vedio_episodes_page_soup.find_all('a', {"class": "meihua_btn"}) print("[开始下载]:"+vedio_name+"---"+vedio_episodes_page_url) #逐集解析 count=0 for vedio_episode_href in vedio_episode_href_list: vedio_episode_url = web_base_url + vedio_episode_href["href"] vedio_episode_html = urlopen(vedio_episode_url).read().decode('utf-8') vedio_episode_soup = BeautifulSoup(vedio_episode_html, features='lxml') count=count+1 vedio_episode_title = "第"+str(count)+"集" vedio_episode_save_path=vedio_save_dir+"/"+vedio_episode_title+".mp4" episode_url = web_base_url + re.findall("video:'(.*?)'",vedio_episode_html)[0] #逐集下载 print("[开始下载]:"+vedio_name+"---"+vedio_episode_title+"---"+episode_url) download_from_url(episode_url,vedio_episode_save_path) print("[下载完成]:"+vedio_name+"---"+vedio_episode_title) except Exception as e: print(e) print("错误，解析url: %s 异常" % vedio_episodes_page_url)
-
Python使用类似JavaScript的对象——EasyDict（更强大的Dict） Python使用类似JavaScript的对象——EasyDict（更强大的Dict）简介用惯 JavaScript 的人上来用 Python 的字典 dict 会很困惑，为什么只能用[]取属性而不能用.呢？JavaScriptvar data = { 'class1': { 'a': {'Chinese': 80}, '小明': {'Chinese': 90}, } }; console.log(data); console.log(data.class1, data['class1']); console.log(data.class1.a, data['class1']['a']); console.log(data.class1.a.Chinese, data['class1']['a']['Chinese']); console.log(data.class1['小明'].Chinese); // 混着用Python 会报错 AttributeError: 'dict' object has no attribute 'xxx'data = { 'class1': { 'a': {'Chinese': 80}, '小明': {'Chinese': 90}, } } print(data) print(data.class1, data['class1']) print(data.class1.a, data['class1']['a']) print(data.class1.a.Chinese, data['class1']['a']['Chinese']) print(data.class1['小明'].Chinese) # 混着用安装pip install easydictPS：可以不安装直接使用源码，仅30行，见文末初试from easydict import EasyDict data = { 'class1': { 'a': {'Chinese': 80}, '小明': {'Chinese': 90}, } } data = EasyDict(data) print(data) print(data.class1, data['class1']) print(data.class1.a, data['class1']['a']) print(data.class1.a.Chinese, data['class1']['a']['Chinese']) print(data.class1['小明'].Chinese) # 混着用 # {'class1': {'a': {'Chinese': 80}, '小明': {'Chinese': 90}}} # {'a': {'Chinese': 80}, '小明': {'Chinese': 90}} {'a': {'Chinese': 80}, '小明': {'Chinese': 90}} # {'Chinese': 80} {'Chinese': 80} # 80 80 # 90 1234567891011121314151617181920 EasyDict` 本质上还是 `Dict from easydict import EasyDict data = EasyDict(log=False) data.debug = True print(data.items()) # dict_items([('log', False), ('debug', True)])EasyDict 源码class EasyDict(dict): def __init__(self, d=None, **kwargs): if d is None: d = {} if kwargs: d.update(**kwargs) for k, v in d.items(): setattr(self, k, v) for k in self.__class__.__dict__.keys(): if not (k.startswith('__') and k.endswith('__')) and not k in ('update', 'pop'): setattr(self, k, getattr(self, k)) def __setattr__(self, name, value): if isinstance(value, (list, tuple)): value = [self.__class__(x) if isinstance(x, dict) else x for x in value] elif isinstance(value, dict) and not isinstance(value, self.__class__): value = self.__class__(value) super(EasyDict, self).__setattr__(name, value) super(EasyDict, self).__setitem__(name, value) __setitem__ = __setattr__ def update(self, e=None, **f): d = e or dict() d.update(f) for k in d: setattr(self, k, d[k]) def pop(self, k, d=None): delattr(self, k) return super(EasyDict, self).pop(k, d)
![[www.cc148.com]小说爬虫](https://blog.inat.top/usr/themes/Joe/assets/thumb/14.jpg)
